--- title: What Is DiskANN? Billion-Scale Vector Search Explained description: DiskANN is a graph-based approximate nearest neighbor (ANN) algorithm from Microsoft Research (NeurIPS 2019) that enables billion-scale vector search by... canonical: https://daily.dev/posts/what-is-diskann-billion-scale-vector-search-explained-6akv6dq0s twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: What Is DiskANN? Billion-Scale Vector Search Explained | daily.dev og:description: DiskANN is a graph-based approximate nearest neighbor (ANN) algorithm from Microsoft Research (NeurIPS 2019) that enables billion-scale vector search by... og:url: https://daily.dev/posts/what-is-diskann-billion-scale-vector-search-explained-6akv6dq0s og:image: https://api.daily.dev/og/posts/6akv6dq0S.png og:image:alt: What Is DiskANN? Billion-Scale Vector Search Explained og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # What Is DiskANN? Billion-Scale Vector Search Explained **[Couchbase](https://daily.dev/sources/couchbase)** · 9 min read · 0 upvotes · 0 comments ## Summary DiskANN is a graph-based approximate nearest neighbor (ANN) algorithm from Microsoft Research (NeurIPS 2019) that enables billion-scale vector search by storing indexes on SSD rather than RAM. Built on the Vamana directed graph algorithm combined with product quantization (PQ), it keeps only compressed vectors in RAM for fast routing while reading full-precision vectors from SSD for final reranking. This achieves 95%+ recall with sub-5ms latency on 1B vectors using just 64GB RAM — 5-10x more vectors per machine than DRAM-only solutions like HNSW. The post covers how DiskANN works, compares it to HNSW and IVF, details tuning parameters (MaxDegree, SearchListSize, BeamWidthRatio), hardware sizing guidelines, and lists databases that support it including Couchbase 8.0, Azure Cosmos DB, Milvus, and pgvectorscale. FreshDiskANN extends the algorithm to support real-time updates without full index rebuilds. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Vector Index DiskANN Embeddings for AI Solutions](https://daily.dev/posts/vector-index-diskann-embeddings-for-ai-solutions-ghudmc57k) · DevBlogs · 0 upvotes · 0 comments - [How to Optimize Vector Search When RAM Gets Too Expensive: On-Disk vs. In-Memory ANN Indexes](https://daily.dev/posts/how-to-optimize-vector-search-when-ram-gets-too-expensive-on-disk-vs-in-memory-ann-indexes-ezniusn01) · Towards Data Science · 0 upvotes · 0 comments --- Tags: [#vector-search](https://daily.dev/tags/vector-search), [#couchbase](https://daily.dev/tags/couchbase) [View this post on daily.dev](https://daily.dev/posts/what-is-diskann-billion-scale-vector-search-explained-6akv6dq0s) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"What Is DiskANN? Billion-Scale Vector Search Explained","url":"https://daily.dev/posts/what-is-diskann-billion-scale-vector-search-explained-6akv6dq0s","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/what-is-diskann-billion-scale-vector-search-explained-6akv6dq0s"},"datePublished":"2026-07-09T07:51:56.123Z","dateModified":"2026-07-09T07:53:13.632Z","description":"DiskANN is a graph-based approximate nearest neighbor (ANN) algorithm from Microsoft Research (NeurIPS 2019) that enables billion-scale vector search by...","image":"https://media.daily.dev/image/upload/s--qPvKM23u--/f_auto/v1722860399/public/Placeholder%2009","thumbnailUrl":"https://media.daily.dev/image/upload/s--qPvKM23u--/f_auto/v1722860399/public/Placeholder%2009","isAccessibleForFree":true,"articleSection":"Couchbase","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Couchbase","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/7bfc4b06cf4f46748cab77d81aa782b6","url":"https://daily.dev/sources/couchbase"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/what-is-diskann-billion-scale-vector-search-explained-6akv6dq0s","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"vector-search,couchbase","timeRequired":"PT9M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Couchbase","item":"https://daily.dev/sources/couchbase"},{"@type":"ListItem","position":3,"name":"What Is DiskANN? Billion-Scale Vector Search Explained"}]} ```